Journal: Genome Biology

Article Title: Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample

doi: 10.1186/s13059-021-02592-9

Figure Lengend Snippet: Performance comparisons on the library preparation and FFPE data sets. a , b F1-score (%) comparison for different somatic mutation callers across different library kits and DNA amounts. Results of different callers for the same library preparation kit and DNA amount are connected for better illustration. c F1-score (%) comparison for different somatic mutation callers on 16 FFPE WGS replicates with FFPE or fresh matched normal. d SNV F1-score (%) comparison for different somatic mutation callers on 14 FFPE WES replicates with FFPE or fresh matched normal. Here, the SEQC-WGS-GT50-SpikeWGS10 trained models were used for NeuSomatic and NeuSomatic-S

Article Snippet: The selected samples included a WGS sample sequenced by a NovaSeq instrument, a WES sample, a sample prepared with a Nextera Flex library-prep kit with 1ng DNA, a 30x WGS sample with 50% tumor purity, a 100x WGS sample with 10% tumor purity, and two WGS and two WES FFPE samples each treated with formalin for 24h and matched with fresh/FFPE normal samples.

Techniques: Comparison, Mutagenesis